From 1da880979412c70f88f34e4c89be3055966edde8 Mon Sep 17 00:00:00 2001
From: Benjamin Wang <benjamin.ahrtr@gmail.com>
Date: Fri, 9 Aug 2024 11:26:15 +0100
Subject: [PATCH] Skip leadership check if the etcd instance is active
 processing heartbeat

Signed-off-by: Benjamin Wang <benjamin.ahrtr@gmail.com>
---
 server/etcdserver/raft.go   | 14 ++++++++++++--
 server/etcdserver/server.go | 16 ++++++++++++++++
 2 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/server/etcdserver/raft.go b/server/etcdserver/raft.go
index d397612af9c4..fd4b5dac3371 100644
--- a/server/etcdserver/raft.go
+++ b/server/etcdserver/raft.go
@@ -80,7 +80,9 @@ type toApply struct {
 type raftNode struct {
 	lg *zap.Logger
 
-	tickMu *sync.Mutex
+	tickMu *sync.RWMutex
+	// timestamp of the latest tick
+	latestTickTs time.Time
 	raftNodeConfig
 
 	// a chan to send/receive snapshot
@@ -132,8 +134,9 @@ func newRaftNode(cfg raftNodeConfig) *raftNode {
 	raft.SetLogger(lg)
 	r := &raftNode{
 		lg:             cfg.lg,
-		tickMu:         new(sync.Mutex),
+		tickMu:         new(sync.RWMutex),
 		raftNodeConfig: cfg,
+		latestTickTs:   time.Now(),
 		// set up contention detectors for raft heartbeat message.
 		// expect to send a heartbeat within 2 heartbeat intervals.
 		td:         contention.NewTimeoutDetector(2 * cfg.heartbeat),
@@ -155,9 +158,16 @@ func newRaftNode(cfg raftNodeConfig) *raftNode {
 func (r *raftNode) tick() {
 	r.tickMu.Lock()
 	r.Tick()
+	r.latestTickTs = time.Now()
 	r.tickMu.Unlock()
 }
 
+func (r *raftNode) getLatestTickTs() time.Time {
+	r.tickMu.RLock()
+	defer r.tickMu.RUnlock()
+	return r.latestTickTs
+}
+
 // start prepares and starts raftNode in a new goroutine. It is no longer safe
 // to modify the fields after it has been started.
 func (r *raftNode) start(rh *raftReadyHandler) {
diff --git a/server/etcdserver/server.go b/server/etcdserver/server.go
index 6708f71bf9af..0600a31b8960 100644
--- a/server/etcdserver/server.go
+++ b/server/etcdserver/server.go
@@ -904,10 +904,26 @@ func (s *EtcdServer) revokeExpiredLeases(leases []*lease.Lease) {
 	})
 }
 
+// isActive checks if the etcd instance is still actively processing the
+// heartbeat message (ticks). It returns false if no heartbeat has been
+// received within 3 * tickMs.
+func (s *EtcdServer) isActive() bool {
+	latestTickTs := s.r.getLatestTickTs()
+	threshold := 3 * time.Duration(s.Cfg.TickMs) * time.Millisecond
+	return latestTickTs.Add(threshold).After(time.Now())
+}
+
 // ensureLeadership checks whether current member is still the leader.
 func (s *EtcdServer) ensureLeadership() bool {
 	lg := s.Logger()
 
+	if s.isActive() {
+		lg.Debug("The member is active, skip checking leadership",
+			zap.Time("latestTickTs", s.r.getLatestTickTs()),
+			zap.Time("now", time.Now()))
+		return true
+	}
+
 	ctx, cancel := context.WithTimeout(s.ctx, s.Cfg.ReqTimeout())
 	defer cancel()
 	if err := s.linearizableReadNotify(ctx); err != nil {